QW

Qwen3 Coder Next REAP 48B A3B

QwenGGUF by lovedheartUpdated 2026-02-08
Download on Hugging Face
Parameters48.9B
Context256K
Layers48
Architectureqwen3next
Smallest quant22.9 GB
Quick answer

Qwen3 Coder Next REAP 48B A3B needs about 39.5 GB of memory at Q5_K_XL (a 38.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 7 quants, from 22.9 GB (Q2_K_XL) to 97.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

48B Qwen3 Coder Next model compressed with REAP for coding tasks

Qwen3 Coder Next REAP 48B A3B is a causal language model with 48.9B total parameters and 3B active parameters. It supports a native context length of 262,144 tokens and is optimized for coding and tool usage. The model is released under the Apache‑2.0 license.

Good at

  • Long‑horizon coding reasoning
  • Tool‑based execution
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Only non‑thinking mode

Best for

  • Local coding agents
  • IDE integration
  • Complex tool workflows

Who it’s for. Developers and researchers building local coding assistants or integrating advanced code generation into IDEs. The model is suitable for users who need large context and efficient inference on local hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_XL22.9 GB 24.2 GB
Too big Get file →
Q3_K_XL27.9 GB 29.2 GB
Too big Get file →
Q4_K_XL33.4 GB 34.7 GB
Too big Get file →
Q5_K_XL38.2 GB 39.5 GB
Too big Get file →
Q6_K_XL43.4 GB 44.7 GB
Too big Get file →
Q8_054.5 GB 55.8 GB
Too big Get file →
BF1697.8 GB (6 parts) 99.1 GB
Too big Get file →

For 8 GB VRAM, use Q2_K_XL (22.89 GB file, ~24.2 GB memory at 8k context). For 16 GB VRAM, Q4_K_XL (33.38 GB file, ~34.7 GB memory) is recommended. Higher‑precision BF16 requires 97.77 GB file and ~99.1 GB memory, suitable only for large‑scale setups.

What GPU do you need for Qwen3 Coder Next REAP 48B A3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is Q3_K_XL (27.9 GB file, about 29.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K_XL (43.4 GB file, about 44.7 GB in use).

Which Qwen3 Coder Next REAP 48B A3B quant should you choose?

Q5_K_XL (38.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q2_K_XL at 22.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3next
Parameters48.9B (approximate, mixture of experts)
Active parameters3B
Layers48
Trained context262,144 tokens
KV cache (fp16)96 KB per token

Source

Quantized bylovedheart
FamilyQwen
Licenseapache-2.0
Downloads (HF)689
Last updated2026-02-08

Frequently asked questions about Qwen3 Coder Next REAP 48B A3B

How much VRAM does Qwen3 Coder Next REAP 48B A3B need?

About 39.5 GB at Q5_K_XL with an 8K context window. That is the 38.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3 Coder Next REAP 48B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3 Coder Next REAP 48B A3B GGUF?

It depends on the quant: Q2_K_XL is 22.9 GB, Q3_K_XL is 27.9 GB, Q4_K_XL is 33.4 GB, Q5_K_XL is 38.2 GB, Q6_K_XL is 43.4 GB, Q8_0 is 54.5 GB and 1 more.

What context length does Qwen3 Coder Next REAP 48B A3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Qwen3 Coder Next REAP 48B A3B GGUF?

The files are on Hugging Face in the lovedheart/Qwen3-Coder-Next-REAP-48B-A3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3 Coder Next REAP 48B A3B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Qwen3 Coder Next REAP 48B A3B on 8 GB VRAM?

Use the Q2_K_XL quantization; the file is 22.89 GB and requires about 24.2 GB memory at 8k context, which fits within 8 GB VRAM when using 8k context.

Does this model support image input?

No, the model does not support vision or image input.

What is the maximum context length?

The native context length is 262,144 tokens.

Other GGUFs of Qwen3-Coder-Next

Similar models

Browse all →

More from lovedheart

All by lovedheart →

More Qwen models

All Qwen →

Other large models

All large models →